A system for categorizing a call between an agent and a caller comprises at least one processor and a memory communicably coupled to the at least one processor. The memory comprises computer executable instructions, which, when executed by the at least one processor implement a method as follows. A call document comprising text of the call between the agent and the caller is received by the system. The system categorizes the call into at least one class using regressive probability analysis of the call document. The system splits the call document to at least two portions, the at least two portions comprising a call header and a call body, and thereafter, using rule-based entity extraction, the system extracts a mandatory entity from the call header and an optional entity from the call body.

Methods for optimizing the routing of customer communications include receiving a customer communication; identifying a customer associated with the customer communication; accessing a profile of the identified customer to determine customer data; receiving customer metric scores for a plurality of customer metrics; identifying available agents; accessing a profile of each available agent to determine agent data; predicting interaction outcome metric values for a plurality of customer metrics based on the customer data and the agent data; calculating, in real-time, an aggregate agent-customer pairing score for each available agent; selecting a responding agent from the available agents with the highest aggregate agent-customer pairing score; and providing a routing recommendation to a communication distributor to route the customer communication to the responding agent with the highest aggregate agent-customer pairing score.

Techniques for benchmarking performance in a contact center system are disclosed. In one particular embodiment, the techniques may be realized as a method for benchmarking contact center system performance comprising cycling, by at least one computer processor configured to perform contact center operations, between a first contact-agent pairing strategy and a second contact-agent pairing strategy for pairing contacts with agents in the contact center system; determining an agent-utilization bias in the first contact-agent pairing strategy comprising a difference between a first agent utilization of the first contact-agent pairing strategy and a balanced agent utilization; and determining a relative performance of the second contact-agent pairing strategy compared to the first contact-agent pairing strategy based on the agent-utilization bias in the first contact-agent pairing strategy.

Video-assisted presence detection is used to enhance a user experience in telephony communications. Image data, video data, or both, from a camera are used to determine whether a user is present at their device before a call is transferred to him or her. The video-assisted presence detection can be implemented based on a privacy setting. For example, one implementation allows a system to have partial access to the camera to perform a scan to detect that there is a human present without capturing facial information, and without identifying that person. Another implementation allows the system to have partial access to the camera to scan the a face of a user, but not have access to the video feed of the camera. Another implementation allows the system to have full access to the camera.

Disclosed implementations use automated transcription and intent detection and an AI model to evaluate interactions between an agent and a customer within a call center environment. The evaluation flow used for manual evaluations is leveraged so that the evaluators can correct the AI evaluations when appropriate. Based on such corrections, the AI model can be retrained to accommodate specifics of the business and center—resulting in more confidence in the AI model over time.

A method and a system for reporting metrics relating to customer calls for fungible agents that are utilizing multiple servicing applications in a contact center environment are provided. The method includes: receiving a service request call from a customer; determining applications that are usable for responding to the service request call from among a predetermined plurality of applications; monitoring the service request call in order to obtain information relating to call timing and events occurring during the call; when the service request call is completed, determining call-specific metrics such as hold time, number of transfers, and or idle time based on the information obtained during the monitoring; and reporting the metrics to a repository. Additional metrics that are specific to an agent assigned to handle the call may also be determined.

Disclosed implementations use automated transcription and intent detection and an AI model to evaluate interactions between an agent and a customer within a call center environment. The evaluation flow used for manual evaluations is leveraged so that the evaluators can correct the AI evaluations when appropriate. Based on such corrections, the AI model can be retrained to accommodate specifics of the business and center—resulting in more confidence in the AI model over time.

Systems and methods for categorizing received calls based on early call information are disclosed. Early call information can be audio, video, other sensor data, or other data collected via a calling device during call setup or any time before the call is routed to or accepted at a receiving device. A call and early call information associated with the call are received. A call characteristic, which can be a purpose or topic of the call, is identified using the early call information. Based on the call characteristic, the received call is categorized and a relative priority for the call is assigned. The call can be routed based on the early call information, and a suggested response to the call can be identified. In some implementations, a machine learning model is trained to categorize received calls based on early call information.

A computerized-method for identifying and utilizing effectiveness of agent handling multiple concurrent multi-channel interactions is provided herein. The computerized-method includes operating of a Multiple Multi-Channel Effectiveness (MME) module. The MME module includes: (a) operating an interaction module to retrieve one or more concurrent interactions of an agent from the data storage of interactions, according to a time range; (b) calculating an MME score for the agent based on metadata of the one or more concurrent interactions which defines the ability of the agent to handle multiple concurrent multi-channel interactions simultaneously; (c) storing the calculated MME score in the data storage of agents; and (d) sending the MME score to the one or more applications to take one or more follow-up actions based on the MME score.

A system may include a processor that may execute computer-executable instructions that cause the processor to receive caller information regarding an incoming communication from a caller and receive a request from a user to route the incoming communication to a virtual assistant application. The virtual assistant application is configured to interact with the caller and determine whether the caller is associated a fraudulent caller activity stored on databases accessible by the processor. The processor may then receive an indication from the virtual assistant application that the caller is associated with the fraudulent caller activity and forward the incoming communication to another party in response to receiving the indication.